4 papers
AttriMem: Attribution-Guided Process Feedback for Agent Memory Construction
Qinfeng Li, Yuntai Bao, Xinyan Yu +8
Effective memory is crucial for LLM agents, yet constructing it effectively remains challenging. A memory-construction policy decides what information to extract, store, update, co…
PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts
Qinfeng Li, Yuntai Bao, Jianghui Hu +5
LLM agents rely on prompts to implement task-specific capabilities based on foundation LLMs, making agent prompts valuable intellectual property. However, in untrusted deployments,…
virtCCA: Virtualized Arm Confidential Compute Architecture with TrustZone
Xiangyi Xu, Wenhao Wang, Yongzheng Wu +7
Arm introduced the Confidential Compute Architecture (CCA) in the upcoming Armv9-A architecture, enabling the support of confidential virtual machines (CVMs) in a separate world ca…
CryptoTensors: A Light-Weight Large Language Model File Format for Highly-Secure Model Distribution
Huifeng Zhu, Shijie Li, Qinfeng Li +1
To enhance the performance of large language models (LLMs) in various domain-specific applications, sensitive data such as healthcare, law, and finance are being used to privately…